Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1701 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.3558. Min Range: -2.3558
Max Act: 2.3558. Min Act: -0.1700
Data Index: 1117792 (C4 (Web Text))
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3558. Min Range: -2.3558
Max Act: 2.3395. Min Act: -0.1700
Data Index: 114619 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3558. Min Range: -2.3558
Max Act: 2.3395. Min Act: -0.1700
Data Index: 947901 (C4 (Web Text))
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3558. Min Range: -2.3558
Max Act: 2.3395. Min Act: -0.1700
Data Index: 360409 (C4 (Web Text))
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3558. Min Range: -2.3558
Max Act: 2.3231. Min Act: -0.1700
Data Index: 1036529 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3558. Min Range: -2.3558
Max Act: 2.3231. Min Act: -0.1700
Data Index: 274415 (C4 (Web Text))
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3558. Min Range: -2.3558
Max Act: 2.3066. Min Act: -0.1700
Data Index: 970785 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3558. Min Range: -2.3558
Max Act: 2.3066. Min Act: -0.1700
Data Index: 513528 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3558. Min Range: -2.3558
Max Act: 2.3066. Min Act: -0.1700
Data Index: 911436 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3558. Min Range: -2.3558
Max Act: 2.3231. Min Act: -0.1700
Data Index: 835403 (C4 (Web Text))
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3558. Min Range: -2.3558
Max Act: 2.3066. Min Act: -0.1700
Data Index: 728958 (C4 (Web Text))
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3558. Min Range: -2.3558
Max Act: 2.3066. Min Act: -0.1700
Data Index: 1198416 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3558. Min Range: -2.3558
Max Act: 2.2737. Min Act: -0.1700
Data Index: 1237557 (C4 (Web Text))
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3558. Min Range: -2.3558
Max Act: 2.2902. Min Act: -0.1700
Data Index: 1114321 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3558. Min Range: -2.3558
Max Act: 2.3066. Min Act: -0.1700
Data Index: 70381 (C4 (Web Text))
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3558. Min Range: -2.3558
Max Act: 2.2902. Min Act: -0.1700
Data Index: 1289535 (C4 (Web Text))
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3558. Min Range: -2.3558
Max Act: 2.2737. Min Act: -0.1700
Data Index: 740982 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3558. Min Range: -2.3558
Max Act: 2.2737. Min Act: -0.1700
Data Index: 682831 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3558. Min Range: -2.3558
Max Act: 2.2737. Min Act: -0.1700
Data Index: 628165 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3558. Min Range: -2.3558
Max Act: 2.2572. Min Act: -0.1700
Data Index: 138253 (C4 (Web Text))
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19